Open Settings > Control groups and click the group's row. The page compares two groups drawn from the same audience:
- Treatment group: users who keep receiving your marketing messages.
- Control group: users held out from marketing messages.
To compare:
- Select a time window: Last 3 days, Last 7 days, or Last 30 days, or pick an ended cycle under Previous.
- Click Add events to compare (up to 10 events). Journey Conversion Goals appear automatically.
- Read Conv. Control, Conv. Treatment, Uplift, and Significance for each event.
- Pick an event in View event to open the Impact report, which adds Conversions driven by messaging, Confidence, P-value, Z-score, and a Group breakdown.
How to read it:
- Significant with positive uplift: messaging drives this event.
- Not significant: the difference isn't reliable yet.
- Not enough data: either group has fewer than 10 conversions or non-conversions.
Things to know:
- Push or email opens, clicks, sends, and bounces can't be compared, because control users never receive marketing messages.
- Data updates once a day.
- Resizing, reshuffling, changing countries or mode, or a cycle ending restarts the measurement window; don't compare results across it.
Learn more: Analyze control group impact
Comments
0 comments
Please sign in to leave a comment.